Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3320 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0353. Min Range: -6.0353

Max Act: 6.0222. Min Act: -0.0000

Data Index: 339166 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 6.0353. Min Range: -6.0353

Max Act: 6.0353. Min Act: -0.0000

Data Index: 23928 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 6.0353. Min Range: -6.0353

Max Act: 5.3918. Min Act: -0.0000

Data Index: 803571 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 6.0353. Min Range: -6.0353

Max Act: 5.4495. Min Act: -0.0000

Data Index: 833386 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 6.0353. Min Range: -6.0353

Max Act: 5.5356. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 6.0353. Min Range: -6.0353

Max Act: 5.2203. Min Act: -0.0000

Data Index: 285177 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.7231. Min Act: -0.0000

Data Index: 139282 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 6.0353. Min Range: -6.0353

Max Act: 5.2096. Min Act: -0.0000

Data Index: 1051307 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.7255. Min Act: -0.0000

Data Index: 541054 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.7090. Min Act: -0.0000

Data Index: 243406 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.6759. Min Act: -0.0000

Data Index: 610671 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.4953. Min Act: -0.0000

Data Index: 449813 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.4522. Min Act: -0.0000

Data Index: 697147 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.7727. Min Act: -0.0000

Data Index: 617046 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.7268. Min Act: -0.0000

Data Index: 435906 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.5605. Min Act: -0.0000

Data Index: 546298 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.5364. Min Act: -0.0000

Data Index: 1152131 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.5372. Min Act: -0.0000

Data Index: 118505 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.7104. Min Act: -0.0000

Data Index: 1347860 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 6.0353. Min Range: -6.0353

Max Act: 4.2334. Min Act: -0.0000

Data Index: 242169 (C4 (Web Text))

Max Activating Token Index: 888